Update app.py

app.py

@@ -18,9 +18,59 @@ DOWNLOAD_DIR.mkdir(parents=True, exist_ok=True)
 DATASET_DIR.mkdir(parents=True, exist_ok=True)
 
 DOWNLOAD_URLS = [
-    "https://youtu.be/ULCkj_Q5NCc?si=P5fVfGeL9dc47tju", "https://youtu.be/WJkI0cds4m4?si=4GlB22ly6RV32q48"
+    "https://youtu.be/wJe9zz_G4js",
+    "https://youtu.be/6RKL-j1k4Dc",
+    "https://youtu.be/tK848ib0BBw",
+    "https://youtu.be/r6ZQil-zd5Y",
+    "https://youtu.be/-gbCSnkvwNo",
+    "https://youtu.be/oso5I277FRY",
+    "https://youtu.be/4haAdmHqGOw",
+    "https://youtu.be/OeGULgqwJh8",
+    "https://youtu.be/QtIfb9JXOJg",
+    "https://youtu.be/lgljOqhhgHg",
+    "https://youtu.be/bokz-7HbgGM",
+    "https://youtu.be/-CiHJ41n6VI",
+    "https://youtu.be/Ys4793edotw",
+    "https://youtu.be/9N87-yRR5aE",
+    "https://youtu.be/5WOrfMz2Sqs",
+    "https://youtu.be/1qVbGr_ie30",
+    "https://youtu.be/qa_1LjeWsJg",
+    "https://youtu.be/9OVvnOh2ZGk",
+    "https://youtu.be/xEpVyEi1Hts",
+    "https://youtu.be/Wg244y2f9Fw",
+    "https://youtu.be/a-4oCHe-hDE",
+    "https://youtu.be/Q30-nakUrSM",
+    "https://youtu.be/HSm-cq7zd2s",
+    "https://youtu.be/x6oWgtJInCQ",
+    "https://youtu.be/9gn_1V1sCS8",
+    "https://youtu.be/dIv2FXyD3CU",
+    "https://youtu.be/SGUBriL9bNU",
+    "https://youtu.be/ABayYXu7OfI",
+    "https://youtu.be/-c0Evpf8V3A",
+    "https://youtu.be/F7VggbBaCsg",
+    "https://youtu.be/cn5BC3Vzcsc",
+    "https://youtu.be/TbjEVSNPiMQ",
+    "https://youtu.be/2PNiRWStZIo",
+    "https://youtu.be/UEeXv1bczuE",
+    "https://youtu.be/mYgznqvbisM",
+    "https://youtu.be/VMLW6XW0k6U",
+    "https://youtu.be/G17sBkp-DIk",
+    "https://youtu.be/XO783U-B5bg",
+    "https://youtu.be/n6V8v5PlvGI",
+    "https://youtu.be/VFSg3DkGSXQ",
+    "https://youtu.be/WgZ1K3J3RGU",
+    "https://youtu.be/DEx1nwxRzXQ",
+    "https://youtu.be/xbKDdRDLhJ8",
+    "https://youtu.be/F5Z8rj-fekU",
+    "https://youtu.be/wkX0z6ygng4",
+    "https://youtu.be/rg-VJGf3Z8E",
+    "https://youtu.be/Bkme3OeK6DM",
+    "https://youtu.be/FsniCv0L-7E",
+    "https://youtu.be/fZrY5n-wqZQ",
+    "https://youtu.be/XGHBtvnvz9U"
 ]
 
+
 USER_AGENTS = [
     "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
     "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Safari/605.1.15",
@@ -30,29 +80,40 @@ COOKIES_FILE = Path("youtube.com_cookies.txt").resolve()  # Place your exported
 RAPIDAPI_HOST = "yt-api.p.rapidapi.com"
 RAPIDAPI_KEY = os.environ.get("RAPIDAPI_KEY", "7b63a42ed4msha215d4e2fb17099p17ae62jsn0f42bd187691")
 PROXY = os.environ.get("198.23.239.134:6540:kknqfmqe:0wyvognccou8")  # Set this environment variable to your proxy, e.g. http://user:pass@host:port
-HF_DATASET_REPO_ID = os.environ.get("Fred808/BG1")
+HF_DATASET_REPO_ID = os.environ.get("HF_DATASET_REPO_ID")
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
 def batch_download_via_api(download_urls, download_dir=DOWNLOAD_DIR):
     """
     Download each video using the public API endpoint and save to download_dir.
+    Use the filename from Content-Disposition if available, else use video ID.
     Also copy to dataset dir and upload to HuggingFace if configured.
     No zipping, just raw mp4s.
     """
-    api_url = "https://fred808-data1.hf.space/batch/download"
+    api_url = "https://fred808-data1.hf.space/video/download"
     for url in download_urls:
         try:
             resp = requests.post(api_url, json={"urls": [url]}, stream=True)
             if resp.status_code == 200:
-                # Try to extract a video ID or use a hash for filename
-                if "v=" in url:
-                    video_id = url.split("v=")[1].split("&")[0]
-                elif "youtu.be/" in url:
-                    video_id = url.split("youtu.be/")[1].split("?")[0]
-                else:
-                    import hashlib
-                    video_id = hashlib.md5(url.encode()).hexdigest()
-                out_path = download_dir / f"{video_id}.mp4"
+                # Try to get filename from Content-Disposition header
+                filename = None
+                cd = resp.headers.get("content-disposition")
+                if cd and "filename=" in cd:
+                    import re
+                    match = re.search(r'filename="?([^";]+)"?', cd)
+                    if match:
+                        filename = match.group(1)
+                if not filename:
+                    # Fallback to video ID
+                    if "v=" in url:
+                        video_id = url.split("v=")[1].split("&")[0]
+                    elif "youtu.be/" in url:
+                        video_id = url.split("youtu.be/")[1].split("?")[0]
+                    else:
+                        import hashlib
+                        video_id = hashlib.md5(url.encode()).hexdigest()
+                    filename = f"{video_id}.mp4"
+                out_path = download_dir / filename
                 with open(out_path, "wb") as f:
                     for chunk in resp.iter_content(chunk_size=8192):
                         if chunk: